Agent RL Research Engineer — Pioneering Post-Training AI

Scale AI, Inc. is recruiting for an Agent MLRE to advance state-of-the-art agent training and building algorithms for enterprise datasets and benchmarks. You will work on applying our Agent RL Training and building methods to real-world data and client benchmarks, delivering high-performance agents.

The role emphasizes post-training approaches (RLHF/RLVR, PPO/GRPO) and producing publishable results from enterprise-scale experiments. Candidates with publications recently are preferred.